Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3425 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1153. Min Act: -0.0003

Data Index: 464713 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1114. Min Act: -0.0003

Data Index: 1099696 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1043. Min Act: -0.0003

Data Index: 808551 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0977. Min Act: -0.0003

Data Index: 414423 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1004. Min Act: -0.0003

Data Index: 313583 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0922. Min Act: -0.0003

Data Index: 497491 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0952. Min Act: -0.0003

Data Index: 1342786 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0974. Min Act: -0.0003

Data Index: 874136 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0948. Min Act: -0.0003

Data Index: 289085 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0937. Min Act: -0.0003

Data Index: 279599 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0941. Min Act: -0.0003

Data Index: 924644 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0936. Min Act: -0.0003

Data Index: 719367 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0924. Min Act: -0.0003

Data Index: 1105601 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0924. Min Act: -0.0003

Data Index: 602494 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0955. Min Act: -0.0003

Data Index: 1027240 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0907. Min Act: -0.0003

Data Index: 21258 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0927. Min Act: -0.0003

Data Index: 1314946 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0924. Min Act: -0.0003

Data Index: 1162639 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0895. Min Act: -0.0003

Data Index: 117313 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0860. Min Act: -0.0003

Data Index: 1177482 (C4 (Web Text))

Max Activating Token Index: 439